Construction Engineering Quality and Safety Supervision System and Method Based on Multi-Source Data

Abstract

The present invention relates to the field of safety supervision technology, and in particular to a construction project quality safety supervision system and method based on multi-source data. The method comprises the following steps: obtaining positioning data of engineering personnel and equipment, identifying motion trajectories and generating a dynamic simulation construction project model to analyze abnormal construction behavior, conducting inducement retrospective analysis to identify the root cause of abnormal behavior, and predicting its development trend, delineating a focused supervision area based on the predicted data, conducting rejection path analysis, forming candidate paths, performing spatial mapping and speed optimization matching on the candidate paths, determining the preferred rejection path, and after evaluating the safety quality of the project, when the safety quality is lower than a threshold, performing project repair management according to the preferred path. The present invention realizes a more efficient and safer construction project quality safety supervision method.

Description

Technical Field

[0001] The present invention relates to the technical field of safety supervision, and in particular to a construction project quality and safety supervision system and method based on multi-source data. Background Art

[0002] With the rapid development of the construction industry, the problems of project safety and quality have become increasingly prominent. Frequent accidents not only affect the project progress, but also cause casualties and property losses. Therefore, it is particularly important to improve the quality and safety supervision level of construction projects. However, traditional supervision methods often rely on manual inspections and regular checks, making it difficult to achieve real-time monitoring and dynamic supervision, resulting in many potential risks not being identified and handled in a timely manner. There are still many challenges in the collection and analysis of data such as the movement trajectories of engineering personnel and equipment, and construction behaviors. Especially in the process of multi-source data fusion, the phenomenon of information islands is serious, resulting in the inability to comprehensively grasp the real-time dynamics of the construction site. In addition, the analysis of the causes of abnormal construction behaviors and the establishment of prediction models are relatively lagging, lacking effective backtracking mechanisms and development prediction means, and it is difficult to provide strong support for decision-making. Summary of the Invention

[0003] Based on this, it is necessary to provide a construction project quality and safety supervision system and method based on multi-source data to solve at least one of the above technical problems.

[0004] To achieve the above object, a construction project quality and safety supervision method based on multi-source data includes the following steps:

[0005] Step S1: Obtain engineering personnel positioning data and engineering equipment positioning data; identify the movement trajectory of engineering personnel positioning data to obtain the personnel movement trajectory; analyze the positioning change of engineering equipment positioning data to generate the equipment movement trajectory;

[0006] Step S2: Perform dynamic construction site simulation based on the personnel movement trajectory and the equipment movement trajectory to generate a dynamic simulation construction project model; analyze the abnormal construction behaviors of the dynamic simulation construction project model to generate construction behavior abnormal data;

[0007] Step S3: Perform cause backtracking analysis on the construction behavior abnormal data to generate abnormal behavior causes; perform abnormal development prediction on the construction behavior abnormal data based on the abnormal behavior causes to obtain predicted abnormal development data;

[0008] Step S4: Cut the dynamic simulation construction project model according to the predicted abnormal development data to generate a focused supervision area; perform exclusion path analysis on the predicted abnormal development data based on the focused supervision area to obtain candidate exclusion paths;

[0009] Step S5: Perform path space mapping on the candidate exclusion paths based on the abnormal construction behavior data to generate abnormal behavior paths; perform speed-optimized exclusion matching on the candidate exclusion paths according to the abnormal behavior paths to obtain the optimized exclusion paths;

[0010] Step S6: Conduct safety and quality assessment based on the predicted abnormal development data to obtain the project safety and quality; when the project safety and quality is lower than the predicted safety and quality threshold, perform project repair management based on the optimized exclusion paths to implement intelligent building project quality and safety supervision.

[0011] The present invention realizes the accurate identification of the movement trajectory by obtaining the positioning data of engineering personnel and equipment. The implementation of the dynamic engineering site simulation generates an intuitive building engineering model. The application of abnormal construction behavior analysis improves the ability to identify potential risks. The cause backtracking analysis provides a clear perspective on the root cause of abnormal behaviors. The generation of abnormal development prediction provides forward-looking information support for construction management. The delineation of the focused supervision area realizes the accurate monitoring of key areas. The implementation of the exclusion path analysis enhances the ability to respond to abnormal situations. The combination of path space mapping and optimized exclusion matching improves the effectiveness of the repair plan. The safety and quality assessment provides a quantitative basis for the overall safety of the project. The finally formed intelligent building project quality and safety supervision system significantly improves the safety and management efficiency of the construction process.

[0012] Preferably, step S1 includes the following steps:

[0013] Step S11: Obtain the positioning data of engineering personnel and the positioning data of engineering equipment;

[0014] Step S12: Mark the points of the personnel positioning data and the engineering equipment positioning data to generate a personnel spatio-temporal point set and an equipment spatio-temporal point set;

[0015] Step S13: Continuize the trajectory of the personnel spatio-temporal point set to obtain a personnel trajectory segment; perform feature fitting processing on the personnel trajectory segment to generate a personnel movement trajectory;

[0016] Step S14: Filter the noise of the equipment spatio-temporal point set to obtain a filtered equipment point set; perform motion vector calculation on the filtered equipment point set to generate an equipment movement trajectory.

[0017] The present invention realizes accurate spatio-temporal point set marking by obtaining the positioning data of engineering personnel and equipment, laying a foundation for subsequent analysis. The trajectory continuous processing of the personnel spatio-temporal point set generates a complete motion trajectory, providing a basis for dynamic monitoring. The feature fitting processing improves the accuracy and reliability of the motion trajectory. Filtering the noise in the equipment point set effectively improves the data quality. The equipment motion trajectory generated by the motion vector calculation provides key data for the monitoring and analysis of the construction process. The overall method improves the safety management efficiency and intelligent level of construction projects.

[0018] Preferably, step S2 includes the following steps:

[0019] Step S21: Obtain engineering terrain data; perform temporal alignment on the motion trajectories of personnel and equipment to obtain synchronized trajectory data;

[0020] Step S22: Perform terrain matching processing on the synchronized trajectory data based on the engineering terrain data to obtain terrain constraint data; perform three-dimensional space reconstruction on the synchronized trajectory data according to the terrain constraint data to obtain a construction site model;

[0021] Step S23: Dynamically evolve the construction site model based on the synchronized trajectory data to generate a dynamic simulation construction project model;

[0022] Step S24: Perform trajectory behavior pattern recognition on the dynamic simulation construction project model to obtain integrated construction behavior characteristics; perform abnormal construction behavior analysis on the integrated construction behavior characteristics to generate construction behavior abnormal data.

[0023] The present invention realizes the temporal alignment of the motion trajectories of personnel and equipment by obtaining engineering terrain data, generates synchronized trajectory data. The terrain matching processing provides terrain constraints for the trajectory data. The construction site model generated by the three-dimensional space reconstruction provides an intuitive basis for subsequent analysis. The dynamically evolving construction project model provides a dynamic view for the real-time monitoring and evaluation of the construction process. The trajectory behavior pattern recognition reveals the construction behavior characteristics. The abnormal data generated by the abnormal construction behavior analysis provides an important basis for risk management. The overall improves the safety monitoring and management efficiency of construction projects.

[0024] Preferably, step S24 includes the following steps:

[0025] Perform spatio-temporal slicing on the dynamic simulation construction project model to obtain model slice data; perform trajectory projection on the model slice data to generate trajectory mapping data;

[0026] Perform behavior pattern recognition on the trajectory mapping data to obtain integrated construction behavior characteristics;

[0027] Identify trajectory collisions for the integrated construction behavior characteristics to obtain trajectory collision data; simulate the trajectory development based on the integrated construction behavior characteristics to obtain trajectory development simulation data;

[0028] Identify trajectory collisions for the trajectory development simulation data to generate trajectory development collision data;

[0029] Screen for abnormal construction behaviors of the integrated construction behavior characteristics based on the trajectory collision data and the trajectory development collision data to generate construction behavior anomaly data.

[0030] The present invention realizes a detailed analysis of the construction process by performing spatio-temporal slicing on a dynamic simulation building engineering model to generate model slice data. The trajectory mapping data generated by the trajectory projection processing provides a basis for further identification. The behavior pattern recognition reveals the characteristics of the construction behavior. The trajectory collision recognition effectively identifies potential safety risks. The trajectory development simulation provides a forward-looking perspective on the dynamic changes of the construction behavior. The secondary collision recognition strengthens the analysis of complex situations. The screening of abnormal construction behaviors based on the collision data provides accurate data support for risk management, and overall improves the safety supervision and management efficiency of the building engineering.

[0031] Preferably, step S3 includes the following steps:

[0032] Step S31: Perform a time series analysis on the construction behavior anomaly data to obtain anomaly correlation chain data;

[0033] Step S32: Trace the sources of the anomaly causes for the anomaly correlation chain data based on a preset standard correlation network to generate anomaly behavior causes;

[0034] Step S33: Perform numerical simulation processing on the anomaly behavior causes to obtain development simulation data; perform trend extrapolation calculation on the development simulation data to obtain anomaly development trend data;

[0035] Step S34: Perform anomaly development prediction based on the anomaly development trend data to obtain predicted anomaly development data.

[0036] The present invention performs a time series analysis on the construction behavior anomaly data to identify the anomaly correlation chain data, providing a basis for subsequent analysis. The cause tracing based on the preset standard correlation network realizes an in-depth exploration of the root causes of the abnormal behaviors. The development simulation data generated by the numerical simulation processing provides a quantitative basis for the dynamic changes of the abnormal behaviors. The trend extrapolation calculation reveals the potential abnormal development trends. The predictive analysis based on the anomaly development trend data provides forward-looking information for construction management, and overall improves the effectiveness of abnormal behavior identification and risk management.

[0037] Preferably, step S32 includes the following steps:

[0038] Perform chain deconstruction processing on the abnormal association chain data to obtain the abnormal chain node distribution;

[0039] Project the abnormal chain node distribution onto a preset standard association network to obtain node matching data;

[0040] Calculate the path interaction degree based on the node matching data to generate an interaction abnormal path; extract the feature incentive node characteristics according to the interaction abnormal path to obtain the feature incentive nodes;

[0041] Construct an abnormal interaction network for the feature incentive nodes according to the preset standard association network to obtain the abnormal interaction network;

[0042] Perform path traceability inversion on the feature incentive nodes based on the abnormal interaction network to generate abnormal behavior incentives.

[0043] Through the chain deconstruction processing of the abnormal association chain data, the present invention identifies the abnormal chain node distribution, providing a detailed basis for subsequent analysis. Projecting the node distribution onto a preset standard association network realizes the generation of node matching data. The interaction abnormal path generated by the path interaction degree calculation reveals the interaction characteristics of abnormal behaviors. The extraction of feature incentive nodes provides key data for in-depth analysis. The construction of the abnormal interaction network realizes a comprehensive perspective on abnormal behaviors. The path traceability inversion provides effective support for identifying abnormal behavior incentives, overall improving the accuracy of abnormal behavior analysis and risk management.

[0044] Preferably, step S4 includes the following steps:

[0045] Step S41: Extract spatial feature data from the predicted abnormal development data to obtain spatial feature data; perform coordinate transformation processing on the spatial feature data to obtain transformed spatial data;

[0046] Step S42: Perform spatial mapping on the transformed spatial data to obtain abnormal influence domain data; perform regional segmentation calculation on the abnormal influence domain data to obtain supervised sub-region data;

[0047] Step S43: Perform risk focusing processing on the supervised sub-region according to the predicted abnormal development data to generate a focused supervision region;

[0048] Step S44: Project the predicted abnormal development data onto the focused supervision region to generate a supervision region trajectory; extend the avoidance trajectory based on the abnormal behavior incentives for the supervision region trajectory to generate an abnormal avoidance trajectory;

[0049] Step S45: Perform path planning on the abnormal avoidance trajectory to generate a candidate rejection path.

[0050] Through the extraction of spatial features from the predicted abnormal development data, the present invention obtains detailed spatial feature data, laying a foundation for subsequent analysis. The transformed spatial data generated by coordinate transformation processing improves the applicability of the data. The abnormal influence domain data obtained by spatial mapping processing provides a spatial perspective for risk assessment. The regulatory sub-region data generated by regional segmentation calculation realizes the refined management of risks. The focused regulatory region generated by risk focusing processing provides a basis for key monitoring. The abnormal trajectory projection enhances the visual analysis of potential risks. The avoidance trajectory extension provides a specific path for implementing risk prevention and control. The candidate exclusion path generated by path planning provides an effective solution for safety management, overall improving the risk management and safety supervision efficiency of construction projects.

[0051] Preferably, step S5 includes the following steps:

[0052] Step S51: Identify the spatial features of the abnormal construction behavior data to obtain abnormal spatial feature data;

[0053] Step S52: Perform spatial feature mapping on the candidate exclusion path based on the abnormal spatial feature data to generate an abnormal behavior path;

[0054] Step S53: Perform similarity matching on the abnormal behavior path and the candidate exclusion path to obtain path similarity data;

[0055] Step S54: Perform path transformation simulation on the abnormal behavior path and the candidate exclusion path according to the path similarity data to obtain a set of simulated path transformations;

[0056] Step S55: Analyze the transformation speed of the set of simulated path transformations to obtain a path transformation speed parameter; perform speed optimization matching on the candidate exclusion path according to the path transformation speed parameter to obtain an optimized exclusion path.

[0057] Through the identification of spatial features of the abnormal construction behavior data, the present invention obtains abnormal spatial feature data, providing a basis for path analysis. Based on these feature data, spatial feature mapping is performed on the candidate exclusion path to generate an abnormal behavior path. Path similarity matching reveals the association between the abnormal behavior and the candidate path, providing a basis for path optimization. The set of transformations generated by path transformation simulation provides a variety of solutions for dynamic management. The speed parameter obtained by transformation speed analysis provides quantitative support for path optimization. Speed optimization matching realizes the refined selection of the candidate exclusion path, overall improving the safety management and risk avoidance capabilities during the construction process of construction projects.

[0058] Preferably, step S6 includes the following steps:

[0059] Step S61: Perform risk quantification processing on the predicted abnormal development data to obtain risk index data;

[0060] Step S62: Perform an engineering safety and quality assessment based on the risk index data to obtain the engineering safety and quality;

[0061] Step S63: Conduct a threshold comparison and analysis on the engineering safety and quality. When the engineering safety and quality is lower than the predicted safety and quality threshold, map the engineering repair plan based on the preferred exclusion path to generate an engineering repair strategy;

[0062] Step S64: Use the engineering repair strategy to perform engineering repair management on the construction project to implement the intelligent building engineering quality and safety supervision.

[0063] Through the risk quantification process of the predicted abnormal development data, the present invention generates risk index data, providing a basis for subsequent evaluations. The engineering safety and quality assessment realizes the comprehensive analysis of the overall safety of the project. The threshold comparison and analysis effectively identify the situation where the safety and quality are lower than expected. The engineering repair plan mapping based on the preferred exclusion path provides a specific strategy for risk management. The implementation of the engineering repair management ensures the quality and safety of the construction project, and overall improves the risk response ability and management efficiency of the construction project.

[0064] The present invention also provides a building engineering quality and safety supervision system based on multi-source data for implementing the building engineering quality and safety supervision method based on multi-source data as described above. The building engineering quality and safety supervision system based on multi-source data includes:

[0065] A safety monitoring module for obtaining engineering personnel positioning data and engineering equipment positioning data; identifying the movement trajectories of engineering personnel based on the engineering personnel positioning data to obtain the personnel movement trajectories; analyzing the positioning changes of the engineering equipment positioning data to generate the equipment movement trajectories;

[0066] An abnormal behavior analysis module for performing dynamic engineering site simulation based on the personnel movement trajectories and equipment movement trajectories to generate a dynamic simulation building engineering model; analyzing abnormal construction behaviors of the dynamic simulation building engineering model to generate construction behavior abnormal data;

[0067] A development prediction module for performing cause backtracking analysis on the construction behavior abnormal data to generate abnormal behavior causes; predicting the abnormal development of the construction behavior abnormal data based on the abnormal behavior causes to obtain predicted abnormal development data;

[0068] A supervision focus module for cutting independent regions of the dynamic simulation building engineering model according to the predicted abnormal development data to generate focused supervision regions; analyzing the exclusion paths of the predicted abnormal development data based on the focused supervision regions to obtain candidate exclusion paths;

[0069] Anomaly avoidance analysis module, which is used to perform path space mapping on candidate exclusion paths based on construction behavior anomaly data to generate anomaly behavior paths; perform speed-optimized exclusion matching on the candidate exclusion paths according to the anomaly behavior paths to obtain optimized exclusion paths;

[0070] Engineering repair management module, which is used to perform safety and quality assessment according to the predicted anomaly development data to obtain the engineering safety and quality; when the engineering safety and quality is lower than the predicted safety and quality threshold, perform engineering repair management based on the optimized exclusion path to implement intelligent building engineering quality and safety supervision.

[0071] The present invention realizes the accurate identification of the movement trajectory by the safety monitoring module to obtain the positioning data of engineering personnel and equipment in real time. The dynamic simulation building engineering model generated by the anomaly behavior analysis module improves the monitoring ability of construction behaviors. The development prediction module reveals the root causes of anomaly behaviors through cause-backtracking analysis, providing a basis for subsequent decision-making. The independent area cutting of the supervision focus module realizes the accurate supervision of key areas. The optimized exclusion path generated by the anomaly avoidance analysis module improves the ability to respond to potential risks. The safety and quality assessment of the engineering repair management module provides a quantitative standard for construction quality. The overall system significantly enhances the safety management efficiency and intelligent level of building engineering. Description of the Drawings

[0072] Figure 1 It is a schematic diagram of the step flow of a building engineering quality and safety supervision method based on multi-source data;

[0073] Figure 2 It is a schematic diagram of the detailed implementation step flow of step S2;

[0074] Figure 3 It is a schematic diagram of the detailed implementation step flow of step S3.

[0075] The realization, functional characteristics and advantages of the purpose of the present invention will be further described in conjunction with the embodiments with reference to the drawings. Detailed Embodiments

[0076] The technical method of the present invention will be clearly and completely described below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0077] In addition, the attached drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0078] It should be understood that although terms such as "first" and "second" may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0079] To achieve the above object, please refer to Figures 1 to 3 , a method for quality and safety supervision of construction projects based on multi-source data, comprising the following steps:

[0080] Step S1: Obtain the positioning data of engineering personnel and the positioning data of engineering equipment; identify the movement trajectories of the engineering personnel positioning data to obtain the personnel movement trajectories; analyze the positioning changes of the engineering equipment positioning data to generate the equipment movement trajectories;

[0081] Step S2: Perform dynamic construction site simulation based on the personnel movement trajectories and the equipment movement trajectories to generate a dynamic simulation construction project model; analyze the abnormal construction behaviors of the dynamic simulation construction project model to generate construction behavior abnormal data;

[0082] Step S3: Perform cause-backtracking analysis on the construction behavior abnormal data to generate abnormal behavior causes; predict the abnormal development of the construction behavior abnormal data based on the abnormal behavior causes to obtain predicted abnormal development data;

[0083] Step S4: Cut the dynamic simulation construction project model into independent regions according to the predicted abnormal development data to generate a focused supervision region; analyze the exclusion paths of the predicted abnormal development data based on the focused supervision region to obtain candidate exclusion paths;

[0084] Step S5: Perform path space mapping on the candidate exclusion paths based on the construction behavior abnormal data to generate abnormal behavior paths; perform speed-optimized exclusion matching on the candidate exclusion paths according to the abnormal behavior paths to obtain optimized exclusion paths;

[0085] Step S6: Perform safety and quality assessment based on the predicted abnormal development data to obtain the engineering safety and quality; when the engineering safety and quality is lower than the predicted safety and quality threshold, perform engineering repair management based on the preferred rejection path to implement intelligent building engineering quality and safety supervision.

[0086] Through obtaining the positioning data of engineering personnel and equipment, the present invention realizes the accurate identification of movement trajectories. The implementation of dynamic engineering site simulation generates an intuitive building engineering model. The application of abnormal construction behavior analysis improves the ability to identify potential risks. The cause backtracking analysis provides a clear perspective on the root cause of abnormal behaviors. The generation of abnormal development prediction provides forward-looking information support for construction management. The delineation of the focused supervision area realizes the accurate monitoring of key areas. The implementation of rejection path analysis enhances the ability to respond to abnormal situations. The combination of path space mapping and preferred rejection matching improves the effectiveness of the repair plan. The safety and quality assessment provides a quantitative basis for the overall safety of the project. The finally formed intelligent building engineering quality and safety supervision system significantly improves the safety and management efficiency of the construction process.

[0087] In the embodiment of the present invention, refer to Figure 1 , which is a schematic diagram of the step flow of the building engineering quality and safety supervision method based on multi-source data of the present invention. In this example, the building engineering quality and safety supervision method based on multi-source data includes the following steps:

[0088] Step S1: Obtain the positioning data of engineering personnel and the positioning data of engineering equipment; perform movement trajectory recognition on the positioning data of engineering personnel to obtain the personnel movement trajectory; perform positioning change analysis on the positioning data of engineering equipment to generate the equipment movement trajectory.

[0089] In this embodiment, to obtain the positioning data of engineering personnel and the positioning data of engineering equipment, high-precision RTK-GNSS receivers (Real-Time Kinematic Global Navigation Satellite System) and Bluetooth beacon devices deployed on the engineering site are used to collect the positioning data of personnel and equipment in real time. The data acquisition module records the time stamp and performs spatial coordinate conversion on the positioning data, and uses the Kalman filtering algorithm to perform dynamic processing on the data to reduce noise and errors. The obtained personnel positioning data is input into the trajectory recognition algorithm through a distributed data processing system. This algorithm performs piecewise fitting of the movement trajectory and classification of behavior patterns based on a multi-time scale path detection model to generate the movement trajectory of engineering personnel. By performing differential analysis on the equipment positioning data, the continuous change information of the equipment displacement is extracted, and the path dynamic optimization algorithm is used to model and fit the equipment movement trajectory to generate the equipment movement trajectory.

[0090] Step S2: Based on the personnel movement trajectory and the equipment movement trajectory, conduct dynamic engineering site simulation to generate a dynamic simulation construction engineering model; analyze the abnormal construction behaviors of the dynamic simulation construction engineering model to generate construction behavior abnormal data;

[0091] In this embodiment, based on the personnel movement trajectory and the equipment movement trajectory, the multi-body dynamics simulation tool MSC Adams software (mechanical simulation analysis tool) is used to model the dynamic engineering behaviors of the engineering site. The two sets of trajectory data are loaded into the three-dimensional site simulation module as input parameters, and the movement process is simulated in real time with discrete time steps through iterative simulation to generate a dynamic simulation construction engineering model that includes the dynamic interaction between personnel and equipment. Through the anomaly detection algorithm integrated in the model, based on logistic regression and support vector machine (SVM) analysis model, the abnormal behaviors of the simulation data stream are identified, and all the data marked as abnormal are grouped and output to generate construction behavior abnormal data.

[0092] Step S3: Conduct cause tracing analysis on the construction behavior abnormal data to generate abnormal behavior causes; based on the abnormal behavior causes, conduct abnormal development prediction on the construction behavior abnormal data to obtain predicted abnormal development data;

[0093] In this embodiment, conduct cause tracing analysis on the construction behavior abnormal data, use the causal analysis model based on Bayesian network to construct an abnormal cause relationship graph, take each group of abnormal data as a leaf node and input it into the analysis model, trace the cause of the abnormality through the backward reasoning method, generate abnormal behavior cause data, conduct time series prediction on the generated abnormal behavior cause data, use the long short-term memory network (LSTM) to model and predict the future development trend of the abnormal cause, and output the predicted abnormal development data.

[0094] Step S4: Cut the dynamic simulation construction engineering model according to the predicted abnormal development data to generate a focused supervision area; based on the focused supervision area, conduct exclusion path analysis on the predicted abnormal development data to obtain candidate exclusion paths;

[0095] In this embodiment, cut the dynamic simulation construction engineering model according to the predicted abnormal development data, use the zoning algorithm to mark the areas with dense abnormal development in the model as the key supervision areas, use the spatial clustering algorithm (such as DBSCAN density clustering) to divide the areas with dense abnormalities, and output the division result as the focused supervision area. Based on the focused supervision area, load the predicted abnormal development data, use the exclusion path analysis tool based on the A* path algorithm to generate multiple candidate exclusion paths in the supervision area, and the candidate paths take the minimum distance from the abnormal point and the minimum detour cost of the obstacle as the optimization objectives.

[0096] Step S5: Perform path space mapping on the candidate exclusion paths based on the abnormal construction behavior data to generate abnormal behavior paths; perform speed-optimized exclusion matching on the candidate exclusion paths according to the abnormal behavior paths to obtain the optimized exclusion paths;

[0097] In this embodiment, based on the abnormal construction behavior data, perform path space mapping on the candidate exclusion paths, use a three-dimensional space geometric model to perform detailed mapping on the interaction area between the candidate paths and the engineering model, supplement and optimize the details of the candidate paths through a local path reconstruction algorithm to generate abnormal behavior paths. According to the abnormal behavior paths, combine path parameters (such as length, detour time, engineering cost) to perform speed-optimized matching on the candidate exclusion paths, use an optimization tool based on the genetic algorithm, and screen the optimal path combination through a path cost function to finally generate the optimized exclusion paths.

[0098] Step S6: Perform safety and quality assessment according to the predicted abnormal development data to obtain the project safety and quality; when the project safety and quality is lower than the predicted safety and quality threshold, perform project repair management based on the optimized exclusion paths to implement intelligent building project quality and safety supervision.

[0099] In this embodiment, according to the predicted abnormal development data, combine with the optimized exclusion paths to comprehensively evaluate the project safety and quality. Use the Fuzzy Analytic Hierarchy Process to construct a safety and quality assessment index system, including indicators such as personnel safety, equipment stability, and abnormal development control effect. Assign weights to each indicator and calculate the safety score, compare the scoring result with the preset safety and quality threshold. When the score is lower than the threshold, design a project repair management plan based on the optimized exclusion paths in Step S5, divide and adjust the parameters of the repair project area through a three-dimensional model editing tool to ensure the feasibility and efficiency of the repair management plan.

[0100] Preferably, Step S1 includes the following steps:

[0101] Step S11: Obtain the engineering personnel positioning data and the engineering equipment positioning data;

[0102] Step S12: Perform point marking on the personnel positioning data and the engineering equipment positioning data to generate a personnel spatio-temporal point set and an equipment spatio-temporal point set;

[0103] Step S13: Continuize the trajectory of the personnel spatio-temporal point set to obtain a personnel trajectory segment; perform feature fitting processing on the personnel trajectory segment to generate a personnel movement trajectory;

[0104] Step S14: Filter the noise of the equipment spatio-temporal point set to obtain a filtered equipment point set; perform motion vector calculation on the filtered equipment point set to generate an equipment movement trajectory.

[0105] In this embodiment, a GNSS (Global Navigation Satellite System) receiver and an IMU (Inertial Measurement Unit) are combined with RTK (Real-Time Kinematic) positioning technology for data collection. The position information of engineering personnel is recorded in real time through the deployed GNSS base station and rover. The data points are recorded at a sampling frequency of 5 Hz to ensure high precision and continuity. At the same time, the positioning module installed on the engineering equipment transmits the position information of the equipment to the central data processing system, and the positioning data is parsed and stored through the data receiving module. Based on the personnel positioning data and the engineering equipment positioning data, the spatio-temporal point marking algorithm is used to process each data stream, and the data points are associated according to the time stamp and spatial coordinates to generate a marked data set. The spatio-temporal point sets of personnel and equipment are stored in the GeoJSON (Geographic Markup Language) format. The KD tree (k-dimensional tree) spatial indexing technology is applied to accelerate the point location search, generating the spatio-temporal point sets of personnel and equipment containing time, space, and marks. The multi-threaded processing technology is used to store the data in slices. For the spatio-temporal point set of personnel, the trajectory reconstruction algorithm is used to perform trajectory continuity processing. The DP (Douglas-Peucker) algorithm is used to simplify the discrete spatio-temporal point set, removing redundant points to generate a more accurate personnel trajectory segment. The trajectory fitting algorithm is used to perform feature extraction and fitting processing on the segment data, and the cubic spline interpolation method is used to calculate the motion characteristic parameters (such as speed, acceleration, and angle change) of each trajectory point to generate the personnel motion trajectory. The noise filtering is performed on the spatio-temporal point set of equipment, and the Gaussian filtering algorithm is used to smooth the point set data. The abnormal points are removed by setting a 3σ threshold (standard deviation threshold) to generate a filtered equipment point set. The motion vector calculation is performed on the filtered equipment point set, and the Euler angles and Quaternion methods are used for attitude estimation. Combining the time step and position change, the motion vector parameters at each moment are calculated, and finally the equipment motion trajectory is generated and stored as a two-dimensional vector graphics file (SVG, Scalable Vector Graphics format) to support the subsequent analysis and optimization process.

[0106] Preferably, step S2 includes the following steps:

[0107] Step S21: Obtain the engineering terrain data; perform temporal alignment on the personnel motion trajectory and the equipment motion trajectory to obtain synchronized trajectory data;

[0108] Step S22: Perform terrain matching processing on the synchronized trajectory data based on the engineering terrain data to obtain terrain constraint data; perform three-dimensional space reconstruction on the synchronized trajectory data according to the terrain constraint data to obtain a construction site model;

[0109] Step S23: Dynamically evolve the construction site model based on the synchronized trajectory data to generate a dynamic simulation construction engineering model;

[0110] Step S24: Identify the trajectory behavior patterns of the dynamic simulation construction engineering model to obtain the integrated construction behavior characteristics; analyze the abnormal construction behaviors of the integrated construction behavior characteristics to generate construction behavior abnormal data.

[0111] In this embodiment, terrain data of the construction site is obtained by a Light Detection and Ranging (LiDAR) device combined with a Global Navigation Satellite System (GNSS). The obtained point cloud data is denoised using a point cloud data processing tool (such as PDAL, Point Cloud Data Abstraction Library). After removing the noise points, the KD-tree (k-dimensional tree) algorithm is used to index the point cloud to generate an engineering terrain data file. A spatial reference system consistent with the personnel movement trajectory and the equipment movement trajectory is established based on the coordinate system of the engineering terrain data. The two types of trajectory data are processed for time series alignment through a timestamp matching algorithm, and each position point in the movement trajectory data is bound to the corresponding time point to generate synchronized trajectory data. The synchronized trajectory data is processed for terrain matching using the engineering terrain data. Through a terrain constraint analysis algorithm based on a Geographic Information System (GIS), the elevation information and tilt angle information in the terrain data are extracted. The position points in the synchronized trajectory data are spatially superimposed on the terrain data to mark whether the trajectory points are located in a feasible area or a restricted area, obtaining terrain constraint data. The terrain constraint data is reconstructed in three-dimensional space through a triangular mesh reconstruction algorithm, and the terrain and trajectory data of the construction site are integrated into a three-dimensional construction site model. The model is stored in the Industry Foundation Classes (IFC) standard to ensure compatibility. A dynamic simulation algorithm is used to perform dynamic evolution processing on the three-dimensional construction site model. Combining the time series information of the synchronized trajectory data, the hourly update of the construction site model is realized through an event-driven dynamic evolution method. The PyChrono library of the Python language is used to perform dynamic simulation processing on the movement trajectory. The model is divided into multiple dynamically updated sub-regions, and each sub-region is independently simulated and then summarized to generate a dynamic simulation construction engineering model. The movement data in the dynamic simulation construction engineering model is analyzed through a trajectory behavior pattern recognition technology. The DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm is used to cluster the trajectory data to extract the movement pattern characteristics of the construction behavior, forming an integrated construction behavior characteristics dataset. Based on the integrated construction behavior characteristics, a classification model based on a Support Vector Machine (SVM) is used to analyze the abnormal construction behaviors. Combining characteristic parameters such as the speed change rate and angle change rate of the trajectory points to determine whether there are abnormalities. The analysis results generate construction behavior abnormal data and are stored as a CSV file for subsequent analysis and optimization processing.

[0112] Preferably, step S24 includes the following steps:

[0113] Perform spatio-temporal slicing on the dynamic simulation building engineering model to obtain model slice data; perform trajectory projection on the model slice data to generate trajectory mapping data;

[0114] Perform behavior pattern recognition on the trajectory mapping data to obtain integrated construction behavior characteristics;

[0115] Perform trajectory collision recognition on the integrated construction behavior characteristics to obtain trajectory collision data; perform trajectory development simulation based on the integrated construction behavior characteristics to obtain trajectory development simulation data;

[0116] Perform trajectory collision recognition on the trajectory development simulation data to generate trajectory development collision data;

[0117] Based on the trajectory collision data and the trajectory development collision data, screen the integrated construction behavior characteristics for abnormal construction behaviors to generate construction behavior anomaly data.

[0118] In this embodiment, by performing spatio-temporal segmentation processing on the three-dimensional data of the dynamic simulation building engineering model, the model is decomposed into multiple independent slice data according to the time series and spatial regions. The time axis is equally spaced by using a technical method based on time step division, and the three-dimensional space of the building model is refined and sliced by combining a spatial grid division tool (such as VTK, Visualization Toolkit). Each slice contains timestamp information and spatial position range, and finally model slice data is generated. The generated model slice data is subjected to trajectory projection processing, and the movement trajectories in the slices are mapped to two-dimensional plane coordinates according to the geographic coordinate system (WGS84). The timestamp of the trajectory points is matched with the slice time range, and the GeoPandas library in the Python language is used to perform spatial projection conversion on the trajectory data. Trajectory mapping data is generated by calculating the projection coordinates of the trajectory points. At the same time, the attribute information of each trajectory such as speed, direction, and acceleration is recorded. The behavior pattern recognition algorithm based on deep learning is applied to the trajectory mapping data. The LSTM (Long Short-Term Memory Network) model that has been pre-trained is used to input the trajectory point sequence to extract the feature vectors of the movement trajectories, and different trajectory patterns are classified. The classification results are associated with the trajectory mapping data to obtain the fused construction behavior features. The trajectory collision detection of the fused construction behavior features is performed by a trajectory collision recognition method based on spatial relationship analysis. The R-tree (R-tree) spatial index is used to quickly search for the neighborhood of the trajectory points, calculate the minimum distance between the trajectory points, and determine whether the collision condition is satisfied. For the trajectory points that meet the conditions, trajectory collision data is generated. The collision data includes time, position, trajectory ID, and collision type information. Based on the fused construction behavior features, the time series of the trajectory points is developed and simulated, and the future position of the trajectory is predicted by using a trajectory simulation algorithm based on physical rules. The development state of the trajectory at different time steps is simulated by the PyChrono library, and the prediction data of the trajectory development process is stored as a dynamic data frame. Finally, the trajectory development simulation data is obtained. The trajectory collision recognition is performed on the trajectory development simulation data, and the same R-tree spatial index and neighborhood search technology as before are used to perform collision analysis on the simulated trajectory data to determine whether there is a collision event in the trajectory at a future moment. Trajectory development collision data is generated and timestamp and trajectory attribute information are attached. The fused construction behavior features are screened for abnormal construction behaviors by combining the trajectory collision data and the trajectory development collision data. By statistically analyzing the characteristics such as the frequency, spatial distribution, and time interval of the trajectory collision events, a classification algorithm based on a decision tree is used to discriminate the abnormal construction behaviors, and the discrimination results are output as construction behavior abnormal data. The construction behavior abnormal data contains the time, position, trajectory, and classification label of the abnormal event, and is finally stored in the CSV file format for further data analysis.

[0119] Preferably, step S3 includes the following steps:

[0120] Step S31: Conduct time series analysis on the abnormal data of construction behaviors to obtain abnormal correlation chain data;

[0121] Step S32: Trace the sources of abnormal incentives for the abnormal correlation chain data based on a preset standard correlation network to generate abnormal behavior incentives;

[0122] Step S33: Perform numerical simulation processing on the abnormal behavior incentives to obtain development simulation data; conduct trend extrapolation calculation on the development simulation data to obtain abnormal development trend data;

[0123] Step S34: Conduct abnormal development prediction based on the abnormal development trend data to obtain predicted abnormal development data.

[0124] In this embodiment, by performing time series analysis on the abnormal construction behavior data, using the time slicing technology based on a sliding window, the abnormal data is segmented at a fixed time step. The pandas library in Python is used to count the event frequencies in the segmented time periods. Combining with the timestamp information of the abnormal events, a time series of abnormal events is constructed. The dynamic time warping algorithm (DTW, Dynamic Time Warping) is used to calculate the time correlation between abnormal events. Further, a causal relationship chain between events is established through a directed acyclic graph model (DAG, Directed Acyclic Graph) to generate abnormal association chain data. Based on a preset standard association network, a network comparison algorithm is used to match the abnormal association chain data with the standard network. A network similarity algorithm based on graph matching is used to calculate the association degree between the abnormal chain and the standard network. The NetworkX library in Python is used to map the nodes and edges in the standard network to the nodes and edges in the abnormal chain one by one. The matching result is transformed into the derivation basis of the abnormal cause. By identifying the key nodes in the abnormal association chain and their corresponding standard network nodes, the abnormal behavior cause is generated, and the specific description of the abnormal cause, including time, event type, and association degree analysis, is recorded in the JSON file format. Numerical simulation processing is performed on the abnormal behavior cause. A multivariate nonlinear dynamic model is used to dynamically simulate the parameters of the abnormal cause. Combining with the historical data of the abnormal cause and the causal relationship in the association chain, a numerical simulation model is constructed by using the Pyomo library (Python optimization modeling). The behavior characteristics and association relationship of the abnormal cause are input into the model for dynamic solution to obtain the development simulation data of the abnormal cause. Trend extrapolation calculation is performed on the development simulation data. A prediction model based on time series is used to extrapolate the development simulation data. Combining with the time series characteristics of the abnormal cause, an LSTM (Long Short-Term Memory) deep learning model is applied to predict the behavior of the abnormal cause in the future time period. The prediction result output by the model is transformed into a trend curve to generate abnormal development trend data. Based on the abnormal development trend data, future development prediction of the abnormal behavior is performed. A Bayesian network is used to further infer the causal relationship of the abnormal development trend. Combining with the classification characteristics of the abnormal cause, a Bayesian inference model in the Scikit-learn library is used to model the future development state of the abnormal behavior. The abnormal development trend data is input into the model for inference calculation, and finally, predicted abnormal development data is generated. The prediction result and the development simulation data are jointly analyzed to obtain predicted abnormal development data including time, space, and abnormal behavior state. All data is stored in a nested JSON file format for subsequent analysis and processing.

[0125] Preferably, step S32 includes the following steps:

[0126] Perform chain deconstruction processing on the abnormal association chain data to obtain the abnormal chain node distribution;

[0127] Project the abnormal chain node distribution onto a preset standard association network to obtain node matching data;

[0128] Calculate the path interaction degree based on the node matching data to generate an interaction abnormal path; extract the feature incentive node characteristics according to the interaction abnormal path to obtain the feature incentive nodes;

[0129] Construct an abnormal interaction network for the feature incentive nodes according to the preset standard association network to obtain the abnormal interaction network;

[0130] Perform path traceability inversion on the feature incentive nodes based on the abnormal interaction network to generate abnormal behavior incentives.

[0131] In this embodiment, through the chain deconstruction process of abnormal correlation chain data, using the chain decomposition algorithm based on graph theory, the nodes in the abnormal correlation chain are deconstructed according to the time series. Based on the timestamp and relevance of the nodes, the order of each node in the chain is disassembled using depth-first search (DFS, Depth First Search), and distributed according to the weight of each node. The time and space characteristics of the nodes are extracted, and the relative position relationship between the nodes is stored in matrix form. Finally, the distribution of abnormal chain nodes is obtained, where the coordinates of each node represent its position and time relationship in the abnormal chain. The abnormal chain node distribution is projected onto a preset standard correlation network. First, a standard network graph is constructed and regarded as an undirected graph, where each node represents an event in the standard correlation network and each edge represents the relationship between events. The node mapping algorithm is used to project the nodes of the abnormal chain onto the standard correlation network, and the cosine similarity-based metric method is used to calculate the similarity between each abnormal chain node and each node in the standard network according to the similarity of the nodes. By selecting the node with the highest similarity for mapping, node matching data is finally generated, including the position of the node on the standard network and its correlation degree. Based on the node matching data, the path interaction degree is calculated. First, the Dijkstra algorithm (shortest path algorithm) is used to calculate the path length from one node to another node, and the interaction degree is calculated according to the interaction frequency and fluidity of the path. By clustering the nodes involved in the path, the clustering center is used to represent the interaction intensity of the path, and an interaction abnormal path is generated. Further, according to the weight of the path, the nodes with higher occurrence frequencies in the path are analyzed, and the node pairs with high interactivity are identified and marked as interaction abnormal paths, and the interaction degree of the path is extracted as a key feature. According to the interaction abnormal path, the feature extraction of the interaction inducing nodes is carried out. Combining the path interaction degree data, a feature extraction method based on signal processing is adopted. The nodes in the path are regarded as signal sources, and wavelet transform is used to process the signals to extract the frequency domain characteristics, time domain characteristics and the relationship characteristics between the nodes of the nodes, and the inducing nodes with abnormal behaviors are identified. The main characteristics of these nodes are extracted, including the event occurrence frequency, duration and the interaction characteristics between the nodes, forming a set of characteristic inducing nodes. According to the preset standard correlation network, an abnormal interaction network is constructed for the characteristic inducing nodes. First, the characteristic inducing nodes are regarded as key nodes in the network, and a network construction method based on topological sorting is used to sort and connect the nodes according to their importance in the network. The connection weight is calculated according to the similarity between the nodes, and the connection structure in the network is adjusted through the edge weight. Finally, an abnormal interaction network is generated, which shows the abnormal interaction relationship of the characteristic inducing nodes in the standard network and can reflect the interaction pattern between the nodes. Based on the abnormal interaction network, the path traceback inversion of the characteristic inducing nodes is carried out,Use the Backpropagation Algorithm to trace the path of the abnormal interaction network, trace the source of the abnormal behavior of the feature incentive node, analyze the causal relationship between nodes, gradually invert the path between nodes, output the traced data and sort it, identify the most probable incentive for the abnormal behavior based on the tracing results, generate the abnormal behavior incentive data, and visually display the results to support subsequent decision-making analysis.

[0132] Preferably, step S4 includes the following steps:

[0133] Step S41: Extract the spatial features of the predicted abnormal development data to obtain spatial feature data; perform coordinate transformation on the spatial feature data to obtain transformed spatial data;

[0134] Step S42: Perform spatial mapping on the transformed spatial data to obtain abnormal influence domain data; perform regional segmentation calculation on the abnormal influence domain data to obtain supervised sub-region data;

[0135] Step S43: Perform risk focusing on the supervised sub-region according to the predicted abnormal development data to generate a focused supervision region;

[0136] Step S44: Project the abnormal trajectory on the predicted abnormal development data based on the focused supervision region to generate a supervision region trajectory; extend the avoidance trajectory based on the abnormal behavior incentive to generate an abnormal avoidance trajectory;

[0137] Step S45: Plan the path for the abnormal avoidance trajectory to generate a candidate rejection path.

[0138] In this embodiment, spatial feature extraction is performed on the predicted abnormal development data. The spatial feature analysis method based on clustering is used to perform clustering analysis on the geographical coordinates of the predicted data. The K-means algorithm is selected to cluster the spatial data, and the cluster centers and cluster radii are obtained. The spatial distances between each cluster center and other points are calculated, and the spatial feature data of each cluster are obtained by calculating features such as the density and distribution pattern of the points. Further, according to the coordinate system of the geographical space, the accurate positions of each spatial feature are calibrated, and the distribution of each spatial feature is represented by a vector map. Coordinate transformation processing is performed on the spatial feature data. The linear transformation method based on coordinate transformation is used to map the points in the original spatial coordinate system to the target coordinate system according to a certain transformation matrix, and operations such as rotation and translation are performed to adapt to the new spatial reference system. Linear transformation is performed on each data point in the original coordinate system to make it conform to the transformed spatial coordinate system. The transformed coordinates are calculated through a four-dimensional transformation matrix (including rotation and translation of the X, Y, and Z axes) to obtain the transformed spatial data. The parameters of the transformation are set according to the differences between the original coordinate system and the target coordinate system. Spatial mapping is performed on the transformed spatial data. The Inverse Mapping Algorithm is used to re-project the transformed spatial data onto a standard two-dimensional or three-dimensional space. Through the method of inverse projection, the transformed spatial coordinates of each data point are mapped back to the original space. The K-Nearest Neighbors (KNN) algorithm is used to map each transformed data point to find the closest standard space node. Finally, the abnormal influence domain data is generated, which reflects the range of the area where abnormal changes occur in the transformed space. Regional segmentation calculation is performed on the abnormal influence domain data. The method based on the Voronoi Diagram is used to divide the space into regions. By using each transformed node as the seed point of the region, the boundaries of each region are calculated to form the segmented region data. The region data is stratified according to the abnormal influence intensity, and the regions with higher influence levels are calibrated. Finally, the supervised sub-region data is obtained. These data can accurately reflect the potential impact of the abnormal region on each link in the essential oil production process. Risk focusing processing is performed on the supervised sub-regions according to the predicted abnormal development data. The risk assessment model optimized by the Genetic Algorithm is used to classify the risk levels of each supervised sub-region according to the abnormal trends of the historical data and the predicted data. By simulating the influence of different behavior patterns on the potential risks in the region, the focused supervision region is generated. Through Cross-validation, the regions with the most potential risks are further screened out. Finally, a supervision region focused on high risks is obtained. Based on the focused supervision region, abnormal trajectory projection is performed on the predicted abnormal development data. The trajectory projection method based on dynamic simulation is used to convert the abnormal development data into trajectory data.Use the Monte Carlo Method to simulate the trajectory, predict the evolution trend of the trajectory in space, correct the trajectory in real time by combining monitoring data, and finally generate abnormal trajectories within the supervised area. These trajectories can reflect the potential impact of the abnormal development trend on the equipment and personnel within the supervised area. Based on the incentives for abnormal behavior, extend the avoidance trajectory of the trajectory within the supervised area. Use the path extension method based on graphic algorithms. By analyzing the impact of the incentives for abnormal behavior on the trajectory, use the Shortest Path Algorithm to extend a new path on the trajectory, simulate the trajectory that avoids the incentives for abnormal behavior. The extended path takes into account multiple factors such as environmental factors and equipment accessibility to generate an abnormal avoidance trajectory. Perform path planning on the abnormal avoidance trajectory, use the A-Star Algorithm to plan the trajectory. By inputting the abnormal avoidance trajectory data and combining the obstacle data of the current area for path planning, given the starting point and the ending point, plan an optimal path, taking into account various constraints such as the layout of production equipment and the width of transportation channels, and finally generate candidate exclusion paths. These paths can minimize the impact of abnormal behavior on the production process while ensuring safety.

[0139] Preferably, step S5 includes the following steps:

[0140] Step S51: Identify the spatial characteristics of the abnormal construction behavior data to obtain abnormal spatial characteristic data;

[0141] Step S52: Perform spatial characteristic mapping on the candidate exclusion path based on the abnormal spatial characteristic data to generate an abnormal behavior path;

[0142] Step S53: Perform similarity matching on the abnormal behavior path and the candidate exclusion path to obtain path similarity data;

[0143] Step S54: Perform path transformation simulation on the abnormal behavior path and the candidate exclusion path according to the path similarity data to obtain a set of simulated path transformations;

[0144] Step S55: Analyze the transformation speed of the set of simulated path transformations to obtain a path transformation speed parameter; perform speed optimization matching on the candidate exclusion path according to the path transformation speed parameter to obtain an optimized exclusion path.

[0145] In this embodiment, spatial feature recognition is performed on the abnormal data of construction behaviors. The convolutional neural network (CNN) based on deep learning is used to extract multi-dimensional features from the data. First, the abnormal data is projected into a three-dimensional space, and the distribution state of the construction abnormal behaviors is represented by establishing a three-dimensional feature matrix. The convolutional kernel is used to extract spatial features layer by layer, and the key feature points of the abnormal data are screened out. The extracted feature data is compared with the standard space model to identify the spatial features of the abnormal behaviors, including information such as position, size, and density. Finally, the abnormal spatial feature data is generated. Based on the abnormal spatial feature data, spatial feature mapping is performed on the candidate exclusion paths. The bidirectional spatial mapping algorithm is used to align the abnormal spatial feature data and the candidate exclusion path data. First, the abnormal spatial feature data is converted into a set of path nodes, and the mapping method based on the shortest path is used to project the abnormal nodes onto the adjacent nodes of the candidate exclusion path. By calculating the distance and direction vector between the path nodes, the abnormal behavior path is generated. This path represents the spatial relationship between the abnormal behavior and the candidate path in the form of a vector diagram, and the deviation in the mapping process is corrected for error to ensure accuracy. Similarity matching is performed on the abnormal behavior path and the candidate exclusion path. The dynamic time warping (DTW) algorithm is used to perform matching analysis on the path data. The abnormal behavior path and the candidate exclusion path are aligned according to the time series, and the similarity value of the two paths is obtained by calculating the Euclidean distance of the path points. The similarity value is stored in matrix form to represent the matching result of each segment of the path. Finally, the path similarity data is generated. This data contains the similarity distribution information of all path points. According to the path similarity data, path transformation simulation is performed on the abnormal behavior path and the candidate exclusion path. The path simulation algorithm based on the Bezier curve is used to dynamically adjust the path data. The abnormal behavior path and the candidate exclusion path are respectively subjected to curve fitting, and the smooth transformation of the path is realized by adjusting the positions of the control points. At the same time, the fitting weight value is adjusted according to the path similarity data to generate a set of simulated path transformations. This set contains the path transformation results under multiple different weight conditions. Transformation speed analysis is performed on the set of simulated path transformations. The method based on the Lagrange interpolation method is used to calculate the speed of the set of path transformations. First, interpolation is performed on the key points of each path to generate a continuous speed change curve, and the transformation speed parameter of the path is calculated by analyzing the slope and curvature of the speed curve. The speed parameter is stored in array form, and each array element represents the speed change value of a certain segment on the path.Perform speed optimization matching on the candidate rejection paths according to the path transformation speed parameter, and select the path with the smoothest transformation speed and meeting the production process requirements as the final optimized rejection path.

[0146] Preferably, step S6 includes the following steps:

[0147] Step S61: Perform risk quantification processing on the predicted abnormal development data to obtain risk index data;

[0148] Step S62: Conduct engineering safety and quality assessment based on the risk index data to obtain the engineering safety and quality;

[0149] Step S63: Conduct threshold comparison and analysis on the engineering safety and quality. When the engineering safety and quality is lower than the predicted safety and quality threshold, map the engineering repair plan based on the optimized rejection path to generate an engineering repair strategy;

[0150] Step S64: Use the engineering repair strategy to conduct engineering repair management on the construction project to implement intelligent construction project quality and safety supervision.

[0151] In this embodiment, risk quantification processing is performed on the predicted abnormal development data. By constructing a multi-layer risk quantification model based on risk factors, the predicted abnormal development data is decomposed into multiple sub-risk factor data. The entropy weight method is used to calculate the weight values of each risk factor. Matrix calculation is performed on the risk factor weights and the prediction data to generate the risk quantification value for each type of abnormality. All the risk quantification values are integrated to obtain the overall risk index data. The risk index data is stored in the CSV file format, and a risk distribution map is generated in combination with a risk chart tool to display the spatial distribution characteristics of the risk quantification results in each region. Engineering safety and quality assessment is carried out based on the risk index data. Using an assessment model based on the Analytic Hierarchy Process (AHP), the risk index data is compared with the engineering quality standards. First, the total risk score is calculated based on the risk index data, and the score is mapped to the engineering safety and quality grade table. The overall safety and quality of the project are comprehensively analyzed in combination with the risk classification weights and regional distribution. During the assessment process, the Matplotlib tool is used to generate a quality assessment map to display the spatial distribution results of the project area safety and quality. The final output of the engineering safety and quality is in the structured JSON file format. Threshold comparison analysis is performed on the engineering safety and quality. When the engineering safety and quality is lower than the predicted safety and quality threshold, an engineering repair plan is mapped based on the preferred exclusion path. By analyzing the matching degree between the structural characteristics of the preferred exclusion path and the actual situation of the project, the path correction algorithm is used to dynamically adjust the path data and generate a preliminary design drawing of the repair plan. Multi-dimensional weight analysis is performed on the design drawing, and the final engineering repair strategy is optimized by combining the risk index and path characteristics. The repair strategy includes the allocation of resources required for repair, time arrangement, and operation guidelines. The engineering repair management of the construction project is carried out using the engineering repair strategy. The intelligent management system based on BIM (Building Information Modeling) is used to decompose the repair strategy. In combination with the repair resource database and the task allocation model, a detailed repair task list is generated and the tasks are assigned to the construction team and the equipment management system. During the construction process, the repair progress and project quality are monitored in real time through intelligent sensors and Internet of Things devices. After the repair is completed, the BIM system is used to perform a secondary assessment of the overall quality of the construction project to ensure that the project quality after repair meets the safety requirements. All construction data and repair records are synchronized to the cloud platform for long-term safety supervision.

[0152] The present invention also provides a building engineering quality and safety supervision system based on multi-source data for implementing the building engineering quality and safety supervision method based on multi-source data as described above. The building engineering quality and safety supervision system based on multi-source data includes:

[0153] A safety monitoring module, which is used to obtain the positioning data of engineering personnel and construction equipment; identify the movement trajectories of engineering personnel based on the positioning data of engineering personnel to obtain the personnel movement trajectories; analyze the positioning changes of the construction equipment positioning data to generate equipment movement trajectories;

[0154] An abnormal behavior analysis module, which is used to perform dynamic engineering site simulation based on the personnel movement trajectories and equipment movement trajectories to generate a dynamic simulation construction engineering model; analyze abnormal construction behaviors of the dynamic simulation construction engineering model to generate construction behavior abnormal data;

[0155] A development prediction module, which is used to perform cause tracing analysis on the construction behavior abnormal data to generate abnormal behavior causes; perform abnormal development prediction on the construction behavior abnormal data based on the abnormal behavior causes to obtain predicted abnormal development data;

[0156] A supervision focus module, which is used to perform independent area cutting on the dynamic simulation construction engineering model according to the predicted abnormal development data to generate a focused supervision area; perform exclusion path analysis on the predicted abnormal development data based on the focused supervision area to obtain candidate exclusion paths;

[0157] An abnormal avoidance analysis module, which is used to perform path space mapping on the candidate exclusion paths based on the construction behavior abnormal data to generate abnormal behavior paths; perform speed-optimized exclusion matching on the candidate exclusion paths according to the abnormal behavior paths to obtain optimized exclusion paths;

[0158] An engineering repair management module, which is used to perform safety and quality assessment according to the predicted abnormal development data to obtain the engineering safety and quality; when the engineering safety and quality is lower than the predicted safety and quality threshold, perform engineering repair management based on the optimized exclusion paths to implement intelligent construction engineering quality and safety supervision.

[0159] Through the safety monitoring module of the present invention, the positioning data of engineering personnel and equipment are obtained in real time, the accurate identification of movement trajectories is realized, the dynamic simulation construction engineering model generated by the abnormal behavior analysis module improves the monitoring ability of construction behaviors, the development prediction module reveals the root causes of abnormal behaviors through cause tracing analysis, providing a basis for subsequent decision-making, the independent area cutting of the supervision focus module realizes the accurate supervision of key areas, the optimized exclusion paths generated by the abnormal avoidance analysis module enhance the ability to respond to potential risks, and the safety and quality assessment of the engineering repair management module provides a quantitative standard for construction quality. The overall system significantly enhances the safety management efficiency and intelligent level of construction projects.

[0160] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to cover all changes falling within the meaning and scope of the equivalent elements of the application documents within the present invention.

[0161] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A building engineering quality and safety supervision method based on multi-source data, characterized in that It includes the following steps: Step S1: Obtain the positioning data of engineering personnel and the positioning data of engineering equipment; Identify the movement trajectory of the engineering personnel positioning data to obtain the personnel movement trajectory; Analyze the positioning change of the engineering equipment positioning data to generate the equipment movement trajectory; Step S2: Perform dynamic engineering site simulation based on the personnel movement trajectory and the equipment movement trajectory to generate a dynamic simulation building engineering model; Analyze the abnormal construction behavior of the dynamic simulation building engineering model to generate construction behavior abnormal data; Among them, step S2 includes the following steps: Step S21: Obtain the engineering terrain data; Align the personnel movement trajectory and the equipment movement trajectory in time sequence to obtain synchronous trajectory data; Step S22: Perform terrain matching processing on the synchronous trajectory data based on the engineering terrain data to obtain terrain constraint data; Reconstruct the three-dimensional space of the synchronous trajectory data according to the terrain constraint data to obtain a construction site model; Step S23: Perform dynamic evolution on the construction site model based on the synchronous trajectory data to generate a dynamic simulation building engineering model; Step S24: Identify the trajectory behavior pattern of the dynamic simulation building engineering model to obtain the integrated construction behavior characteristics; Analyze the abnormal construction behavior of the integrated construction behavior characteristics to generate construction behavior abnormal data, where step S24 includes: Perform spatio-temporal slicing on the dynamic simulation building engineering model to obtain model slice data; Perform trajectory projection on the model slice data to generate trajectory mapping data; Perform behavior pattern recognition on the trajectory mapping data to obtain the integrated construction behavior characteristics; Perform trajectory collision recognition on the integrated construction behavior characteristics to obtain trajectory collision data; Simulate the trajectory development based on the integrated construction behavior characteristics to obtain trajectory development simulation data; Perform trajectory collision recognition on the trajectory development simulation data to generate trajectory development collision data; ​ ​ ​ ​ ​ 2. The method for supervision of the quality and safety of construction projects based on multi-source data according to claim 1, wherein ​ ​ Step S12: Perform point marking on the personnel positioning data and engineering equipment positioning data to generate a personnel spatio-temporal point set and an equipment spatio-temporal point set; Step S13: Continuize the trajectories of the personnel spatio-temporal point set to obtain personnel trajectory segments; perform feature fitting processing on the personnel trajectory segments to generate a personnel movement trajectory; Step S14: Filter the noise of the equipment spatio-temporal point set to obtain a filtered equipment point set; calculate the motion vectors of the filtered equipment point set to generate an equipment movement trajectory; 3. The method for supervising the quality and safety of construction projects based on multi-source data according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Perform time series analysis on the construction behavior abnormal data to obtain abnormal correlation chain data; Step S32: Trace the abnormal causes of the abnormal correlation chain data based on a preset standard correlation network to generate abnormal behavior causes; Step S33: Perform numerical simulation processing on the abnormal behavior causes to obtain development simulation data; perform trend extrapolation calculation on the development simulation data to obtain abnormal development trend data; Step S34: Perform abnormal development prediction based on the abnormal development trend data to obtain predicted abnormal development data.

4. The method for supervising the quality and safety of construction projects based on multi-source data according to claim 3, characterized in that Step S32 includes the following steps: Perform chain deconstruction processing on the abnormal correlation chain data to obtain the abnormal chain node distribution; Project the abnormal chain node distribution onto a preset standard correlation network to obtain node matching data; Calculate the path interaction degree based on the node matching data to generate an interaction abnormal path; extract the feature cause nodes according to the interaction abnormal path; Construct an abnormal interaction network for the feature cause nodes according to a preset standard correlation network to obtain an abnormal interaction network; Perform path tracing inversion on the feature cause nodes based on the abnormal interaction network to generate abnormal behavior causes.

5. The method for supervising the quality and safety of construction projects based on multi-source data according to claim 1, characterized in that, Step S4 includes the following steps: Step S41: Extract spatial features from the predicted abnormal development data to obtain spatial feature data; perform coordinate transformation processing on the spatial feature data to obtain transformed spatial data; Step S42: Perform spatial mapping on the transformed spatial data to obtain abnormal influence domain data; perform regional segmentation calculation on the abnormal influence domain data to obtain supervised sub-region data; Step S43: Perform risk focusing processing on the supervised sub-regions according to the predicted abnormal development data to generate a focused supervision region; Step S44: Perform abnormal trajectory projection on the predicted abnormal development data based on the focused supervision region to generate a supervision region trajectory; extend the avoidance trajectory based on the abnormal behavior causes to generate an abnormal avoidance trajectory; Step S45: Perform path planning on the abnormal avoidance trajectory to generate candidate exclusion paths.

6. The method for building engineering quality and safety supervision based on multi-source data according to claim 1, characterized in that, Step S5 includes the following steps: Step S51: Identify the spatial features of the construction behavior abnormal data to obtain abnormal spatial feature data; Step S52: Perform spatial feature mapping on the candidate exclusion paths based on the abnormal spatial feature data to generate abnormal behavior paths; Step S53: Perform similarity matching on the abnormal behavior paths and the candidate exclusion paths to obtain path similarity data; Step S54: Perform path transformation simulation on the abnormal behavior paths and the candidate exclusion paths according to the path similarity data to obtain a simulated path transformation set; Step S55: Analyze the transformation speed of the simulated path transformation set to obtain the path transformation speed parameter; perform speed-optimal matching on the candidate rejection paths according to the path transformation speed parameter to obtain the optimal rejection paths.

7. The method for supervision of construction project quality and safety based on multi-source data according to claim 1, characterized in that, Step S6 includes the following steps: Step S61: Perform risk quantification processing on the predicted abnormal development data to obtain risk index data; Step S62: Perform engineering safety and quality assessment according to the risk index data to obtain the engineering safety and quality; Step S63: Conduct threshold comparison and analysis on the engineering safety and quality. When the engineering safety and quality is lower than the predicted safety quality threshold, map the engineering repair plan based on the optimal rejection path to generate an engineering repair strategy; Step S64: Use the engineering repair strategy to perform engineering repair management on the construction project to implement the intelligent construction project quality and safety supervision.

8. A building engineering quality and safety supervision system based on multi-source data, characterized in that, For implementing the construction project quality and safety supervision method based on multi-source data as described in Claim 1, the construction project quality and safety supervision system based on multi-source data includes: A safety monitoring module, configured to obtain the engineering personnel positioning data and the engineering equipment positioning data; identify the movement trajectory of the engineering personnel positioning data to obtain the personnel movement trajectory; perform positioning change analysis on the engineering equipment positioning data to generate the equipment movement trajectory; An abnormal behavior analysis module, configured to perform dynamic engineering site simulation based on the personnel movement trajectory and the equipment movement trajectory to generate a dynamic simulation construction project model; perform abnormal construction behavior analysis on the dynamic simulation construction project model to generate construction behavior abnormal data; A development prediction module, configured to perform cause-backtracking analysis on the construction behavior abnormal data to generate abnormal behavior causes; perform abnormal development prediction on the construction behavior abnormal data based on the abnormal behavior causes to obtain the predicted abnormal development data; A supervision focus module, configured to perform independent area cutting on the dynamic simulation construction project model according to the predicted abnormal development data to generate a focused supervision area; perform rejection path analysis on the predicted abnormal development data based on the focused supervision area to obtain candidate rejection paths; An abnormal avoidance analysis module, configured to perform path space mapping on the candidate rejection paths based on the construction behavior abnormal data to generate abnormal behavior paths; perform speed-optimal rejection matching on the candidate rejection paths according to the abnormal behavior paths to obtain the optimal rejection paths; An engineering repair management module, configured to perform safety and quality assessment according to the predicted abnormal development data to obtain the engineering safety and quality; when the engineering safety and quality is lower than the predicted safety quality threshold, perform engineering repair management based on the optimal rejection path to implement the intelligent construction project quality and safety supervision.

Images